© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20911
    Prev
    Next
    INDEX
    Explanations

    accidents and death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĩªå¦Ĥ
    -0.10
    imore
    -0.10
    æķijæµİ
    -0.10
    éĻį
    -0.09
    åħį
    -0.09
    è¢«åĽ°
    -0.09
    èĥ´
    -0.09
    achable
    -0.09
    wyn
    -0.09
    å¼Ģåħĥ
    -0.08
    POSITIVE LOGITS
    车祸
    0.14
     accident
    0.12
    交éĢļäºĭæķħ
    0.10
     accidents
    0.10
    éĿ¢çĽ®
    0.09
    æĶ«
    0.09
    çħ¤æ°Ķ
    0.09
     undef
    0.08
    被人
    0.08
    (acc
    0.08
    Activations Density 0.142%

    No Known Activations